arXiv:2607. 20473v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly released as open-weight models with safeguards against harmful requests.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
The paper investigates a continuation-triggered jailbreak in large language models, showing that moving an instruction suffix can markedly boost jailbreak success. By performing mechanistic interpretability at the attention‑head level, the authors reveal that the jailbreak arises from a competition between the model’s natural continuation drive and safety defenses learned during alignment. They introduce Head Competition Steering (HCS), an inference‑time technique that exploits this competition to suppress harmful outputs and distill the approach into a student model for efficient safety improvements.
arXiv:2609.26185v1 Announce Type: cross Abstract: Large Language Models (LLMs) demonstrate impressive capabilities across many applications but remain vulnerable to jailbreak attacks, which elicit ha...
arXiv:2606. 07963v1 Announce Type: new Abstract: Backdoor attacks in large language models (LLMs) are often treated as isolated trigger-response failures, motivating defenses tailored to specific triggers or behaviors.
arXiv:2606. 25182v1 Announce Type: cross Abstract: Jailbreak attacks reveal a persistent weakness in aligned Large Language Models: carefully crafted prompts can elicit policy-violating responses despite safety training.
arXiv:2605.27110v2 Announce Type: replace-cross Abstract: In this work, we propose BAIT (Boundary-Aware Iterative Trap), a three-step jailbreak framework that elicits malicious information through in...
arXiv:2609.35356v2 Announce Type: replace Abstract: Supervised fine-tuning can teach language models undesired behaviours alongside desired ones. Inoculation prompting (IP) aims to limit unwanted gen...